Safe Reinforcement Learning for Sepsis Treatment.
Yan JiaJohn BurdenTom LawtonIbrahim HabliPublished in: ICHI (2020)
Keyphrases
- reinforcement learning
- function approximation
- initial stage
- multi agent
- direct policy search
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- state space
- data sets
- control problems
- model free
- markov decision processes
- learning process
- temporal difference learning
- supervised learning
- dynamic programming
- control system
- learning capabilities
- machine learning
- policy search
- medical treatment
- real time